Align metric names with Prometheus naming conventions

Use base units, export cumulative values as _total counters, update docs, dashboards and rules.

metrics/pve_node_virtual_machine_collector.go

@@ -26,20 +26,20 @@ type PveVirtualMachineCollector struct {
 	diskMax *TTLGaugeVec // Virtual machine disk size in bytes prometheus gauge.
 	swap    *TTLGaugeVec // Virtual machine swap usage in bytes prometheus gauge.
 
-	netReceive  *TTLGaugeVec // Virtual machine network receive in bytes prometheus gauge.
-	netTransmit *TTLGaugeVec // Virtual machine network transmit in bytes prometheus gauge.
+	netReceive  *TTLCounterVec // Virtual machine received network traffic in bytes prometheus counter.
+	netTransmit *TTLCounterVec // Virtual machine transmitted network traffic in bytes prometheus counter.
 
-	diskReadOps  *TTLGaugeVec // Virtual machine disk read ops prometheus gauge.
-	diskWriteOps *TTLGaugeVec // Virtual machine disk write ops prometheus gauge.
+	diskReadOps  *TTLCounterVec // Virtual machine disk read operations prometheus counter.
+	diskWriteOps *TTLCounterVec // Virtual machine disk write operations prometheus counter.
 
-	diskReadBytes  *TTLGaugeVec // Virtual machine disk read bytes prometheus gauge.
-	diskWriteBytes *TTLGaugeVec // Virtual machine disk write bytes prometheus gauge.
+	diskReadBytes  *TTLCounterVec // Virtual machine disk read bytes prometheus counter.
+	diskWriteBytes *TTLCounterVec // Virtual machine disk written bytes prometheus counter.
 
-	diskReadTimeNs  *TTLGaugeVec // Virtual machine disk read time total prometheus gauge.
-	diskWriteTimeNs *TTLGaugeVec // Virtual machine disk write time total prometheus gauge.
+	diskReadTime  *TTLCounterVec // Virtual machine disk read time total in seconds prometheus counter.
+	diskWriteTime *TTLCounterVec // Virtual machine disk write time total in seconds prometheus counter.
 
-	diskFailedReadOps  *TTLGaugeVec // Virtual machine disk failed read ops prometheus gauge.
-	diskFailedWriteOps *TTLGaugeVec // Virtual machine disk failed write ops prometheus gauge.
+	diskFailedReadOps  *TTLCounterVec // Virtual machine failed disk read operations prometheus counter.
+	diskFailedWriteOps *TTLCounterVec // Virtual machine failed disk write operations prometheus counter.
 
 	agent *TTLGaugeVec // Virtual machine agent enabled prometheus gauge.
 }
@@ -63,8 +63,8 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	// Virtual machine uptime.
 	c.uptime = NewTTLGaugeVec(
 		prometheus.GaugeOpts{
-			Name: "pve_vm_uptime",
-			Help: "Virtual machine uptime.",
+			Name: "pve_vm_uptime_seconds",
+			Help: "Virtual machine uptime in seconds.",
 		},
 		[]string{"cluster", "node", "vmid", "name"},
 		5*time.Minute,
@@ -85,7 +85,7 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	// Virtual machine CPU count.
 	c.cpu = NewTTLGaugeVec(
 		prometheus.GaugeOpts{
-			Name: "pve_vm_cpu_count",
+			Name: "pve_vm_cpus",
 			Help: "Virtual machine CPU count.",
 		},
 		[]string{"cluster", "node", "vmid", "name"},
@@ -96,8 +96,8 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	// Virtual machine CPU usage.
 	c.cpuUsage = NewTTLGaugeVec(
 		prometheus.GaugeOpts{
-			Name: "pve_vm_cpu_usage",
-			Help: "Virtual machine CPU usage.",
+			Name: "pve_vm_cpu_usage_ratio",
+			Help: "Virtual machine CPU usage ratio (0-1).",
 		},
 		[]string{"cluster", "node", "vmid", "name"},
 		5*time.Minute,
@@ -107,7 +107,7 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	// Virtual machine memory total.
 	c.memBytes = NewTTLGaugeVec(
 		prometheus.GaugeOpts{
-			Name: "pve_vm_mem_total_bytes",
+			Name: "pve_vm_memory_total_bytes",
 			Help: "Virtual machine total memory in bytes.",
 		},
 		[]string{"cluster", "node", "vmid", "name"},
@@ -118,7 +118,7 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	// Virtual machine memory usage.
 	c.memBytesUsed = NewTTLGaugeVec(
 		prometheus.GaugeOpts{
-			Name: "pve_vm_mem_used_bytes",
+			Name: "pve_vm_memory_used_bytes",
 			Help: "Virtual machine used memory in bytes.",
 		},
 		[]string{"cluster", "node", "vmid", "name"},
@@ -129,8 +129,8 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	// Virtual machine disk size.
 	c.disk = NewTTLGaugeVec(
 		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_usage_bytes",
-			Help: "Virtual machine disk read bytes.",
+			Name: "pve_vm_disk_used_bytes",
+			Help: "Virtual machine used disk space in bytes.",
 		},
 		[]string{"cluster", "node", "vmid", "name"},
 		5*time.Minute,
@@ -149,10 +149,10 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.diskMax)
 
 	// Virtual machine network receive bytes.
-	c.netReceive = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_network_in_bytes",
-			Help: "Virtual machine network receive in bytes.",
+	c.netReceive = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_network_receive_bytes_total",
+			Help: "Virtual machine received network traffic in bytes.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "interface"},
 		5*time.Minute,
@@ -160,10 +160,10 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.netReceive)
 
 	// Virtual machine network transmit bytes.
-	c.netTransmit = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_network_out_bytes",
-			Help: "Virtual machine network transmit in bytes.",
+	c.netTransmit = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_network_transmit_bytes_total",
+			Help: "Virtual machine transmitted network traffic in bytes.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "interface"},
 		5*time.Minute,
@@ -171,10 +171,10 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.netTransmit)
 
 	// Virtual machine disk read ops.
-	c.diskReadOps = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_rd_operations",
-			Help: "Virtual machine disk read ops.",
+	c.diskReadOps = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_read_operations_total",
+			Help: "Virtual machine disk read operations.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
 		5*time.Minute,
@@ -182,10 +182,10 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.diskReadOps)
 
 	// Virtual machine disk write ops.
-	c.diskWriteOps = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_wr_operations",
-			Help: "Virtual machine disk write ops.",
+	c.diskWriteOps = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_write_operations_total",
+			Help: "Virtual machine disk write operations.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
 		5*time.Minute,
@@ -193,9 +193,9 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.diskWriteOps)
 
 	// Virtual machine disk read bytes.
-	c.diskReadBytes = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_rd_bytes",
+	c.diskReadBytes = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_read_bytes_total",
 			Help: "Virtual machine disk read bytes.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
@@ -204,9 +204,9 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.diskReadBytes)
 
 	// Virtual machine disk write bytes.
-	c.diskWriteBytes = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_wr_bytes",
+	c.diskWriteBytes = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_write_bytes_total",
 			Help: "Virtual machine disk write bytes.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
@@ -215,10 +215,10 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.diskWriteBytes)
 
 	// Virtual machine failed disk read ops.
-	c.diskFailedReadOps = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_failed_rd_ops",
-			Help: "Virtual machine failed disk read ops.",
+	c.diskFailedReadOps = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_failed_read_operations_total",
+			Help: "Virtual machine failed disk read operations.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
 		5*time.Minute,
@@ -226,37 +226,37 @@ func NewPveVirtualMachineCollector(apiClient *proxmox.PveApiClient, registry *TT
 	c.registry.Register(c.diskFailedReadOps)
 
 	// Virtual machine failed disk write ops.
-	c.diskFailedWriteOps = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_failed_wr_ops",
-			Help: "Virtual machine failed disk write ops.",
+	c.diskFailedWriteOps = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_failed_write_operations_total",
+			Help: "Virtual machine failed disk write operations.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
 		5*time.Minute,
 	)
 	c.registry.Register(c.diskFailedWriteOps)
 
-	// Virtual machine disk read time total nanoseconds.
-	c.diskReadTimeNs = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_rd_time_total_ns",
-			Help: "Virtual machine disk read time total in nanoseconds.",
+	// Virtual machine disk read time total seconds.
+	c.diskReadTime = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_read_time_seconds_total",
+			Help: "Virtual machine disk read time total in seconds.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
 		5*time.Minute,
 	)
-	c.registry.Register(c.diskReadTimeNs)
+	c.registry.Register(c.diskReadTime)
 
-	// Virtual machine disk write time total nanoseconds.
-	c.diskWriteTimeNs = NewTTLGaugeVec(
-		prometheus.GaugeOpts{
-			Name: "pve_vm_disk_wr_time_total_ns",
-			Help: "Virtual machine disk write time total in nanoseconds.",
+	// Virtual machine disk write time total seconds.
+	c.diskWriteTime = NewTTLCounterVec(
+		prometheus.CounterOpts{
+			Name: "pve_vm_disk_write_time_seconds_total",
+			Help: "Virtual machine disk write time total in seconds.",
 		},
 		[]string{"cluster", "node", "vmid", "name", "device"},
 		5*time.Minute,
 	)
-	c.registry.Register(c.diskWriteTimeNs)
+	c.registry.Register(c.diskWriteTime)
 
 	return &c
 }
@@ -336,8 +336,8 @@ func (c *PveVirtualMachineCollector) CollectMetrics() error {
 					c.diskFailedReadOps.With(labels).Set(float64(value.FailedRdOperations))
 					c.diskFailedWriteOps.With(labels).Set(float64(value.FailedWrOperations))
 
-					c.diskReadTimeNs.With(labels).Set(float64(value.RdTotalTimeNs))
-					c.diskWriteTimeNs.With(labels).Set(float64(value.WrTotalTimeNs))
+					c.diskReadTime.With(labels).Set(float64(value.RdTotalTimeNs) / float64(time.Second))
+					c.diskWriteTime.With(labels).Set(float64(value.WrTotalTimeNs) / float64(time.Second))
 				}
 			}
 		}